sched/fair: Consider spare capacity in find_idlest_group()

In low-utilization scenarios comparing relative loads in
find_idlest_group() doesn't always lead to the most optimum choice.
Systems with groups containing different numbers of cpus and/or cpus of
different compute capacity are significantly better off when considering
spare capacity rather than relative load in those scenarios.

In addition to existing load based search an alternative spare capacity
based candidate sched_group is found and selected instead if sufficient
spare capacity exists. If not, existing behaviour is preserved.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dietmar.eggemann@arm.com
Cc: freedom.tan@mediatek.com
Cc: keita.kobayashi.ym@renesas.com
Cc: mgalbraith@suse.de
Cc: sgurrappadi@nvidia.com
Cc: vincent.guittot@linaro.org
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/1476452472-24740-3-git-send-email-morten.rasmussen@arm.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -5202,6 +5202,14 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 	return 1;
 }
 
+static inline int task_util(struct task_struct *p);
+static int cpu_util_wake(int cpu, struct task_struct *p);
+
+static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
+{
+	return capacity_orig_of(cpu) - cpu_util_wake(cpu, p);
+}
+
 /*
  * find_idlest_group finds and returns the least busy CPU group within the
  * domain.
@@ -5211,7 +5219,9 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		  int this_cpu, int sd_flag)
 {
 	struct sched_group *idlest = NULL, *group = sd->groups;
+	struct sched_group *most_spare_sg = NULL;
 	unsigned long min_load = ULONG_MAX, this_load = 0;
+	unsigned long most_spare = 0, this_spare = 0;
 	int load_idx = sd->forkexec_idx;
 	int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
@@ -5219,7 +5229,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		load_idx = sd->wake_idx;
 
 	do {
-		unsigned long load, avg_load;
+		unsigned long load, avg_load, spare_cap, max_spare_cap;
 		int local_group;
 		int i;
 
@@ -5231,8 +5241,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		local_group = cpumask_test_cpu(this_cpu,
 					       sched_group_cpus(group));
 
-		/* Tally up the load of all CPUs in the group */
+		/*
+		 * Tally up the load of all CPUs in the group and find
+		 * the group containing the CPU with most spare capacity.
+		 */
 		avg_load = 0;
+		max_spare_cap = 0;
 
 		for_each_cpu(i, sched_group_cpus(group)) {
 			/* Bias balancing toward cpus of our domain */
@@ -5242,6 +5256,11 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 				load = target_load(i, load_idx);
 
 			avg_load += load;
+
+			spare_cap = capacity_spare_wake(i, p);
+
+			if (spare_cap > max_spare_cap)
+				max_spare_cap = spare_cap;
 		}
 
 		/* Adjust by relative CPU capacity of the group */
@@ -5249,12 +5268,33 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 
 		if (local_group) {
 			this_load = avg_load;
-		} else if (avg_load < min_load) {
+			this_spare = max_spare_cap;
+		} else {
+			if (avg_load < min_load) {
 				min_load = avg_load;
 				idlest = group;
 			}
+
+			if (most_spare < max_spare_cap) {
+				most_spare = max_spare_cap;
+				most_spare_sg = group;
+			}
+		}
 	} while (group = group->next, group != sd->groups);
 
+	/*
+	 * The cross-over point between using spare capacity or least load
+	 * is too conservative for high utilization tasks on partially
+	 * utilized systems if we require spare_capacity > task_util(p),
+	 * so we allow for some task stuffing by using
+	 * spare_capacity > task_util(p)/2.
+	 */
+	if (this_spare > task_util(p) / 2 &&
+	    imbalance*this_spare > 100*most_spare)
+		return NULL;
+	else if (most_spare > task_util(p) / 2)
+		return most_spare_sg;
+
 	if (!idlest || 100*this_load < imbalance*min_load)
 		return NULL;
 	return idlest;